Instructions to use zai-org/cogagent-chat-hf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use zai-org/cogagent-chat-hf with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="zai-org/cogagent-chat-hf", trust_remote_code=True)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("zai-org/cogagent-chat-hf", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use zai-org/cogagent-chat-hf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "zai-org/cogagent-chat-hf"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "zai-org/cogagent-chat-hf",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/zai-org/cogagent-chat-hf

SGLang

How to use zai-org/cogagent-chat-hf with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "zai-org/cogagent-chat-hf" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "zai-org/cogagent-chat-hf",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "zai-org/cogagent-chat-hf" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "zai-org/cogagent-chat-hf",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use zai-org/cogagent-chat-hf with Docker Model Runner:
```
docker model run hf.co/zai-org/cogagent-chat-hf
```

zR commited on Dec 24, 2024

Commit

26eec27

verified ·

1 Parent(s): 0e33dcb

Update README.md

Browse files

Files changed (1) hide show

README.md +8 -4

README.md CHANGED Viewed

@@ -5,13 +5,17 @@ language:
 ---
 # CogAgent
-**News**: The new version `CogAgent-9B-20241220` has been released! Welcome to visit [CogAgent GitHub](https://github.com/THUDM/CogAgent) and [Technical Report](https://cogagent.aminer.cn/blog#/articles/cogagent-9b-20241220-technical-report-en) to explore and use our latest model.
-**CogAgent** is an open-source visual language model improved based on **CogVLM**.
 📖 Paper: https://arxiv.org/abs/2312.08914
-🚀 GitHub: For more information such as demo, fine-tuning, and query prompts, please refer to [Our GitHub](https://github.com/THUDM/CogVLM/)
 ## Reminder

 ---
 # CogAgent
+**🔥 News**: The new version `CogAgent-9B-20241220` has been released! Welcome to visit [CogAgent GitHub](https://github.com/THUDM/CogAgent) and [Technical Report](https://cogagent.aminer.cn/blog#/articles/cogagent-9b-20241220-technical-report-en) to explore and use our latest model.
 📖 Paper: https://arxiv.org/abs/2312.08914
+📄 Technical Report: https://cogagent.aminer.cn/blog#/articles/cogagent-9b-20241220-technical-report-en
+🚀 GitHub: https://github.com/THUDM/CogAgent
+🤗 Model Page: https://huggingface.co/THUDM/cogagent-9b-20241220
+**CogAgent** is an open-source visual language model improved based on **CogVLM**. For more information such as demo, fine-tuning of `THUDM/cogagent-chat-hf`, and query prompts, please refer to [This GitHub](https://github.com/THUDM/CogVLM/)
 ## Reminder